Regional traffic forecasting is a critical challenge in urban mobility, with applications to various fields such as the Internet of Everything. In recent years, spatio-temporal graph neural networks have achieved state-of-the-art results in the context of numerous traffic forecasting challenges. This work aims to expand upon the conventional spatio-temporal graph neural network architectures in a manner that may facilitate the inclusion of information regarding the examined regions and the populations that traverse them to establish a more efficient prediction model. The end-product of this scientific endeavor is a novel spatio-temporal graph neural network architecture for regional traffic forecasting referred to as WEST (WEighted STacked) GCN-LSTM. Furthermore, the aforementioned information is included via two novel dedicated algorithms, the Shared Borders Policy and the Adjustable Hops Policy. Through information fusion and distillation, the proposed solution significantly outperforms its competitors in an experimental evaluation of 19 forecasting models across several datasets. Finally, an additional ablation study determined that each component of the proposed solution enhances its overall performance.

Top